last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0085470085470085,
  "eval_steps": 25,
  "global_step": 22,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13675213675213677,
      "grad_norm": NaN,
      "learning_rate": 9.954196488464198e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.13675213675213677,
      "eval_loss": NaN,
      "eval_runtime": 0.6566,
      "eval_samples_per_second": 76.145,
      "eval_steps_per_second": 19.798,
      "step": 1
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": NaN,
      "learning_rate": 9.81771838126524e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": NaN,
      "learning_rate": 9.593343979095333e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": NaN,
      "learning_rate": 9.285640897740315e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": NaN,
      "learning_rate": 8.900873084594164e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": NaN,
      "learning_rate": 8.446873302753784e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": NaN,
      "learning_rate": 7.93288367855019e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 1.0940170940170941,
      "grad_norm": NaN,
      "learning_rate": 7.369367558508489e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": NaN,
      "learning_rate": 6.767796505786435e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 1.3675213675213675,
      "grad_norm": NaN,
      "learning_rate": 6.140416772229784e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 1.5042735042735043,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": NaN,
      "learning_rate": 4.859583227770218e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": NaN,
      "learning_rate": 4.232203494213567e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 1.9145299145299144,
      "grad_norm": NaN,
      "learning_rate": 3.630632441491512e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": NaN,
      "learning_rate": 3.067116321449813e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 2.1880341880341883,
      "grad_norm": NaN,
      "learning_rate": 2.5531266972462177e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 2.324786324786325,
      "grad_norm": NaN,
      "learning_rate": 2.0991269154058385e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": NaN,
      "learning_rate": 1.7143591022596845e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 2.5982905982905984,
      "grad_norm": NaN,
      "learning_rate": 1.4066560209046673e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 2.735042735042735,
      "grad_norm": NaN,
      "learning_rate": 1.1822816187347623e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 2.871794871794872,
      "grad_norm": NaN,
      "learning_rate": 1.0458035115358032e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 3.0085470085470085,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 22
    }
  ],
  "logging_steps": 1,
  "max_steps": 22,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1550434850308096.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}